Machine Learning Based Outlook for the Analysis of SNP-SNP Interaction for Biomedical Big Data

Abstract

In the field of biomedical sciences, it is much essential to discover the mode of gene interaction and their environment in context to their influence over a particular genetic trait. The Single Nucleotide Polymorphisms (SNPs) are the variations encountered in DNA sequence generated due to single nucleotide alteration in genomic sequence. Recently, Genome-Wide Association Studies(GWAS) have revealed the significant associations between SNPs and disease. To be categorized as mutation, it must occur among at least 1% of the population. SNPs are the most common form of variation occurring in a population. Studies show evidence that the key reason behind complex disease development is SNP-SNP interactions, not individual SNPs. Several models have been developed and implemented for the analysis of SNP-SNP interactions. This paper presents the understanding of big data analytics in the field of biomedical and healthcare along with the different machine learning methods implemented for SNP-SNP interactions analysis studies. These analysis methods and models enable us to acquire more comprehensive understanding of human physiology and disease relation.